Now showing 1 - 3 of 3
  • Publication
    A Mood-based Genre Classification of Television Content
    The classification of television content helps users organise and navigate through the large list of channels and programs now available. In this paper, we address the problem of television content classification by exploiting text information extracted from program transcriptions. We present an analysis which adapts a model for sentiment that has been widely and successfully applied in other fields such as music or blog posts. We use a real-world dataset obtained from the Box- fish API to compare the performance of classifiers trained on a number of different feature sets. Our experiments show that, over a large collection of television content, program genres can be represented in a three-dimensional space of valence, arousal and dominance, and that promising classification results can be achieved using features based on this representation. This finding supports the use of the proposed representation of television content as a feature space for similarity computation and recommendation generation.
  • Publication
    Evaluating the Relative Performance of Neighbourhood-Based Recommender Systems
    Neighbourhood-based recommender systems are a class of collaborative filtering algorithms, which rely on finding like-minded users to generate recommendations, automating what is usually known as word-of-mouth. These systems attempt to solve the information overload problem by presenting the user with relevant items. However, there is evidence showing that these algorithms may contribute to the filter bubble problem, making it harder for the user to find interesting items which are non-popular. In this paper we propose a novel evaluation of the performance and biases of the two most common neighbourhood-based approaches: user k-nearest neighbour collaborative filtering (UKNN ), and item k-nearest neighbour collaborative filtering (IKNN). We propose an evaluation which considers the size of the neighbourhood, finding that optimising for accuracy in UKNN algorithms leads to a poor performance in terms of diversity, a higher bias towards popularity, and less unique recommendations, when compared to the IKNN approach.
  • Publication
    An Exploration of Mood Classification in the Million Songs Dataset
    (Music Technology Research Group, Department of Computer Science, Maynooth University, 2015-08-01) ;
    As the music consumption paradigm moves towards streamingservices, users have access to increasingly large catalogsof music. In this scenario, music classification playsan important role in music discovery. It enables, for example, search by genres or automatic playlist creation based on mood. In this work we study the classification of songmood, using features extracted from lyrics alone, basedon a vector space model representation. Previous work inthis area reached contradictory conclusions based on experimentscarried out using different datasets and evaluationmethodologies. In contrast, we use a large freelyavailabledataset to compare the performance of differentterm-weighting approaches from a classification perspective.The experiments we present show that lyrics can successfullybe used to classify music mood, achieving accuraciesof up to 70% in some cases. Moreover, contraryto other work, we show that the performance of the differentterm weighting approaches evaluated is not statisticallydifferent using the dataset considered. Finally, we discuss the limitations of the dataset used in this work, and the need for a new benchmark dataset to progress work in this area.